© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12226
    Prev
    Next
    INDEX
    Explanations

    references to error and its quantification in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.84
    enterOuterAlt
    -0.84
    Portail
    -0.83
    isContained
    -0.83
     angekommen
    -0.76
     tramonto
    -0.74
     antaranya
    -0.73
     Portail
    -0.69
     frattempo
    -0.68
    YourGuide
    -0.68
    POSITIVE LOGITS
     error
    3.16
     Error
    2.81
     errors
    2.70
     Errors
    2.49
    error
    2.45
     ERROR
    2.38
    Error
    2.36
    Errors
    2.11
    errors
    2.03
     erro
    1.95
    Activations Density 0.113%

    No Known Activations